3D Rome created from 150,000 Flickr photos
Scientists from the University of Washington have used advanced photo analysis and modelling techniques to generate fly-though representations of the Colosseum, the Trevi fountain and the Croatian city of Dubrovnik.
The models are created entirely from data taken from images uploaded by members of the public on to the photo-sharing website.
The team used a specially-devised algorithm to detect and arrange photos showing various angles of the same building. The same algorithm then analysed these images - taking into account the viewpoint of the photographer - to produce composite 3D models.
Rome's most famous landmarks were generated in less than 24 hours from 150,000 photos, while 250,000 images were scanned to make 3D models of Venice.
Read entire article at telegraph.co.uk
The models are created entirely from data taken from images uploaded by members of the public on to the photo-sharing website.
The team used a specially-devised algorithm to detect and arrange photos showing various angles of the same building. The same algorithm then analysed these images - taking into account the viewpoint of the photographer - to produce composite 3D models.
Rome's most famous landmarks were generated in less than 24 hours from 150,000 photos, while 250,000 images were scanned to make 3D models of Venice.